echotorch.nn¶
Echo State Layers¶
ESNCell¶
-
class
nn.
ESNCell
(input_dim, output_dim, spectral_radius=0.9, bias_scaling=0, input_scaling=1.0, w=None, w_in=None, w_bias=None, w_fdb=None, sparsity=None, input_set=[1.0, -1.0], w_sparsity=None, nonlin_func=<built-in function tanh>, feedbacks=False, feedbacks_dim=None, wfdb_sparsity=None, normalize_feedbacks=False, seed=None, w_distrib='uniform', win_distrib='uniform', wbias_distrib='uniform', win_normal=(0.0, 1.0), w_normal=(0.0, 1.0), wbias_normal=(0.0, 1.0), dtype=torch.float32)¶ Echo State Network layer
-
forward
(u, y=None, w_out=None, reset_state=True)¶ Forward :param u: Input signal :param y: Target output signal for teacher forcing :param w_out: Output weights for teacher forcing :return: Resulting hidden states
-
static
generate_gaussian_matrix
(size, sparsity, mean=0.0, std=1.0, dtype=torch.float32)¶ Generate gaussian Win matrix :return:
-
static
generate_uniform_matrix
(size, sparsity, input_set)¶ Generate uniform Win matrix :param w_in: :param seed: :return:
-
static
generate_w
(output_dim, w_distrib='uniform', w_sparsity=None, mean=0.0, std=1.0, seed=None, dtype=torch.float32)¶ Generate W matrix :param output_dim: :param w_sparsity: :return:
-
get_spectral_radius
()¶ Get W’s spectral radius :return: W’s spectral radius
Init hidden layer :return: Initiated hidden layer
Reset hidden layer :return:
Set hidden layer :param x: :return:
-
static
to_sparse
(m)¶ To sparse matrix :param m: :return:
-
ESN¶
-
class
nn.
ESN
(input_dim, hidden_dim, output_dim, spectral_radius=0.9, bias_scaling=0, input_scaling=1.0, w=None, w_in=None, w_bias=None, w_fdb=None, sparsity=None, input_set=[1.0, -1.0], w_sparsity=None, nonlin_func=<built-in function tanh>, learning_algo='inv', ridge_param=0.0, create_cell=True, feedbacks=False, with_bias=True, wfdb_sparsity=None, normalize_feedbacks=False, softmax_output=False, seed=None, washout=0, w_distrib='uniform', win_distrib='uniform', wbias_distrib='uniform', win_normal=(0.0, 1.0), w_normal=(0.0, 1.0), wbias_normal=(0.0, 1.0), dtype=torch.float32)¶ Echo State Network module
-
finalize
()¶ Finalize training with LU factorization
-
forward
(u, y=None, reset_state=True)¶ Forward :param u: Input signal. :param y: Target outputs :return: Output or hidden states
-
get_spectral_radius
()¶ Get W’s spectral radius :return: W’s spectral radius
-
get_w_out
()¶ Output matrix :return:
Hidden layer :return:
-
reset
()¶ Reset learning :return:
Reset hidden layer :return:
-
set_w
(w)¶ Set W :param w: :return:
-
w
¶ Hidden weight matrix :return:
-
w_in
¶ Input matrix :return:
-
LiESNCell¶
LiESN¶
-
class
nn.
LiESN
(input_dim, hidden_dim, output_dim, spectral_radius=0.9, bias_scaling=0, input_scaling=1.0, w=None, w_in=None, w_bias=None, sparsity=None, input_set=[1.0, -1.0], w_sparsity=None, nonlin_func=<built-in function tanh>, learning_algo='inv', ridge_param=0.0, leaky_rate=1.0, train_leaky_rate=False, feedbacks=False, wfdb_sparsity=None, normalize_feedbacks=False, softmax_output=False, seed=None, washout=0, w_distrib='uniform', win_distrib='uniform', wbias_distrib='uniform', win_normal=(0.0, 1.0), w_normal=(0.0, 1.0), wbias_normal=(0.0, 1.0), dtype=torch.float32)¶ Leaky-Integrated Echo State Network module